Search Results for author: Shen Cai

Found 6 papers, 5 papers with code

An Efficient End-to-End 3D Voxel Reconstruction based on Neural Architecture Search

1 code implementation27 Feb 2022 Yongdong Huang, Yuanzhan Li, Xulong Cao, Siyu Zhang, Shen Cai, Ting Lu, Jie Wang, Yuqi Liu

However, many previous works employ neural networks with fixed architecture and size to represent different 3D objects, which lead to excessive network parameters for simple objects and limited reconstruction accuracy for complex objects.

Binary Classification Neural Architecture Search +1

High-fidelity 3D Model Compression based on Key Spheres

1 code implementation19 Jan 2022 Yuanzhan Li, Yuqi Liu, Yujie Lu, Siyu Zhang, Shen Cai, Yanting Zhang

Compared to previous works, our method achieves the high-fidelity and high-compression 3D object coding and reconstruction.

Model Compression Vocal Bursts Intensity Prediction

Spherical Transformer: Adapting Spherical Signal to CNNs

no code implementations11 Jan 2021 Yuqi Liu, Yin Wang, Haikuan Du, Shen Cai

To this end, the proposed method first uses local structured sampling methods such as HEALPix to construct a transformer grid by using the information of spherical points and its adjacent points, and then transforms the spherical signals to the vectors through the grid.

3D Object Classification General Classification +2

InSphereNet: a Concise Representation and Classification Method for 3D Object

1 code implementation25 Dec 2019 Hui Cao, Haikuan Du, Siyu Zhang, Shen Cai

Unlike previous methods that use points, voxels, or multi-view images as inputs of deep neural network (DNN), the proposed method constructs a class of more representative features named infilling spheres from signed distance field (SDF).

3D Object Classification Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.